feat: implement inline autocomplete suggestions with FastAPI backend and Milkdown editor integration

backend/llm.py

@@ -0,0 +1,44 @@
+import os
+from typing import AsyncGenerator
+from openai import AsyncOpenAI
+import json
+
+api_key = os.getenv('OPENAI_API_KEY', 'ollama')
+base_url = os.getenv('OLLAMA_BASE_URL', 'http://192.168.0.120:11434/v1/')
+model = os.getenv('OLLAMA_MODEL', 'gpt-oss:120b')
+
+print(f"[LLM] API key configured: {'Yes' if api_key else 'No'}")
+print(f"[LLM] Base URL: {base_url}")
+print(f"[LLM] Model: {model}")
+
+client = AsyncOpenAI(api_key=api_key, base_url=base_url)
+
+async def stream_openai(prompt: str) -> AsyncGenerator[str, None]:
+    """
+    调用 OpenAI/Ollama API 并流式返回补全内容。
+    参考 completions-sample-code 的 streaming 逻辑。
+    """
+    print(f"[LLM] Calling API with prompt length: {len(prompt)}")
+    
+    try:
+        stream = await client.chat.completions.create(
+            model=model,
+            messages=[{"role": "user", "content": prompt}],
+            stream=True,
+            max_tokens=128,
+            temperature=0.2,
+        )
+
+        chunk_count = 0
+        async for chunk in stream:
+            if chunk.choices[0].delta.content:
+                content = chunk.choices[0].delta.content
+                chunk_count += 1
+                print(f"[LLM] Chunk {chunk_count}: {content}")
+                yield json.dumps({"content": content})
+        
+        print(f"[LLM] Stream complete, total chunks: {chunk_count}")
+    except Exception as e:
+        error_msg = f"Error: {str(e)}"
+        print(f"[LLM] Error: {error_msg}")
+        yield json.dumps({"error": str(e)})